AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging

Huimin Cheng, Xiaowei Yu, Shushan Wu, Luyang Fang, Chao Cao, Jing Zhang, Tianming Liu, Dajiang Zhu, Wenxuan Zhong, Ping Ma

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add entropy regularization on soft memberships (ablation)DCMM-Transformer · Average over 5 medical datasetsaccuracy (%): 84.4 -> 87.3Improved
add degree correction (node degree parameters) (ablation)DCMM-Transformer · Average over 5 medical datasetsaccuracy (%): 85.0 -> 87.3Improved
add mixed-membership (soft memberships) (ablation)DCMM-Transformer · Average over 5 medical datasetsaccuracy (%): 84.7 -> 87.3Improved
add entropy regularization (ablation)DCMM-Transformer · ADNIaccuracy (%): 66.7 -> 74.1Improved
add degree correction (ablation)DCMM-Transformer · ChestXrayaccuracy (%): 94.9 -> 96.0Improved
add DCMM additive bias to ViT-S attention (vs plain ViT)DCMM-Transformer · Average over 5 medical datasetsaccuracy (%): 83.6 -> 87.3Improved
replace SBM-Transformer binary masking with DCMM additive biasDCMM-Transformer · Average over 5 medical datasetsaccuracy (%): 83.1 -> 87.3Improved
DCMM bias vs MaxViT (best baseline)DCMM-Transformer · EyeDiseaseaccuracy (%): 93.2 -> 93.3No clear effect
vary number of communities L from 80 to 180 (ablation)DCMM-Transformer · INbreast, EyeDisease, ChestXrayaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy